Anthropic Excessive Chat Snapshot Creation

edit
IMPORTANT: This documentation is no longer updated. Refer to Elastic's version policy and the latest documentation.

Anthropic Excessive Chat Snapshot Creation

edit

Detects an unusually high number of successful Claude chat snapshot creation events for the same user email within a rolling 24-hour window. Chat snapshots package conversation content into shareable exports; sustained creation volume can indicate staging of organizational chat data for exfiltration via Anthropic’s web service or automated bulk export of sensitive prompts and responses.

Rule type: esql

Rule indices: None

Severity: medium

Risk score: 47

Runs every: 1h

Searches indices from: now-24h (Date Math format, see also Additional look-back time)

Maximum alerts per execution: 100

References:

Tags:

  • Domain: GenAI
  • Platform: Anthropic
  • Data Source: Anthropic Audit Logs
  • Use Case: Threat Detection
  • Use Case: UEBA
  • Resources: Investigation Guide
  • Rule Type: ES|QL
  • Tactic: Exfiltration

Version: 1

Rule authors:

  • Elastic

Rule license: Elastic License v2

Investigation guide

edit

Triage and analysis

Investigating Anthropic Excessive Chat Snapshot Creation

One mailbox created many chat snapshots in 24 hours. Snapshots can package conversation content for handoff — or for exfiltration staging. Source IP/UA are investigation fields, not grouping keys, so multi-IP bursts still accumulate.

Escalate when scripting UA, concurrent file uploads / public artifact sharing / data exports / chat deletions appear, or snapshots span many unrelated chats. Close as FP for documented knowledge handoffs, training packaging, or compliance archival automation.

Possible investigation steps

  • Review event count and snapshot/chat ID lists — many distinct chats is stronger than repeated snapshots of one chat.
  • Inspect IP/UA values for automation. Correlate with uploads, public artifact sharing, exports, or deletions from the same email.
  • Note actor type and whether the same email appears across organizations (organization_id values).

False positive analysis

  • Power-user archival and compliance snapshot jobs commonly exceed the threshold.

Response and remediation

  • On unauthorized staging: revoke sessions, review snapshot destinations and shared links, and tighten chat sharing or export policy for the actor.

Rule query

edit
from logs-anthropic.audit-*
| where
    data_stream.dataset == "anthropic.audit" and
    mv_contains(event.category, "file") and
    event.action == "claude_chat_snapshot_created" and
    event.outcome == "success" and
    user.email is not null
| stats
    Esql.event_count = count(*),
    Esql.event_id_values = values(event.id),
    Esql.anthropic_audit_claude_chat_snapshot_id_values = values(anthropic.audit.claude_chat_snapshot_id),
    Esql.anthropic_audit_claude_chat_id_values = values(anthropic.audit.claude_chat_id),
    Esql.source_ip_values = values(source.ip),
    Esql.user_agent_original_values = values(user_agent.original),
    Esql.anthropic_audit_actor_type_values = values(anthropic.audit.actor.type),
    Esql.organization_id_values = values(organization.id),
    Esql.user_id_values = values(user.id),
    Esql.timestamp_first_seen = min(@timestamp),
    Esql.timestamp_last_seen = max(@timestamp)
  by user.email
| where Esql.event_count >= 10
| keep user.email, Esql.*

Framework: MITRE ATT&CKTM